Congratulations for the project, finally able to run something useful locally using this project

[rodjjo]

Congratulations for the team and the contributors 🗡️

I was testing the limits of this project, for that I used Deepseek Harness along with ornith 1.5 35B A3B and this FreeToken.

Got a good cache 262144 and 15 to 19 tokens per seconds (RTX 5070ti 16GB, 96GB system ram)

The project https://github.com/rodjjo/pimbalgame
I validated using this #354

Not related to this project the only thing I saw was this funny thing (related to the model, not the project):

At the end the model just created a python script to concatenate "set" + "Scale" to fix the C++ files :D

Thanks, Hope we have support for vision and MTP for this model :)

[MT-z]

Congratulations — I built it and ran it here, and read the repo alongside it. The thing that stayed
with me is that you got here without vision.

A pinball table is close to the least forgiving thing to build with a model that cannot see the
screen. Every bug in it is something you watch happen and then have to render into prose before the
model can act on it. Your commit messages are the proof:

a slow ball settled forever in the valley between the flipper and the adjacent wall

below y=700 the left side was only the diagonal guide, so a ball returning down the lane could
slip past the left of the plunger pad and drain

Those are one screenshot each, and instead they are paragraphs — carefully measured ones, with
coordinates. A complete C++17 game with its own SVG-to-atlas asset pipeline, out of a 35B model with
~3B active on a 16 GB card, built that way. Thank you for posting it rather than just running it — I would not have seen it otherwise.

Which brings me to vision

I see vision is listed on the roadmap (#79). In the meantime I have been running the 3.5-family
path locally, and reading your issue I could not resist: I took a screenshot of your table and fed it to Ornith.
I would rather leave what came back for you to find — I suspect you will enjoy it.

The branch is
feat/vision-qwen3_5-full —
nine commits on current main, served with --vision. It is not upstream.

What I can tell you is only what I have seen here: the vision tower is ~0.8 GiB of resident bf16 on
this checkpoint.

_{Written with AI assistance; everything above was run on my own hardware (RTX 4090, sm_89).}

[rodjjo]

@MT-z Thanks! I'll tryout your branch.

By the way I added audio support to pinball game :D. When I said "I did" I mean the "model did", I did nothing except typing prompt on to create that program, even the commits, the pushes, the docs were created by the model itself. I installed https://en.wikipedia.org/wiki/Xvfb to have a "x environment" inside the sandbox, so the graphical application could run there, the model could map the screen into png then open with python read the pixels in numpy to see the pixels values.

The SVG were created by the model as well, i told it to create a tool to convert into png and put it inside the program as a header.
I'm just trying the limits of it.

[rodjjo]

@MT-z Thanks, I was able to test your changes 🗡️

[MT-z]

Your Xvfb-and-numpy account stayed with me, and it turned into two commits on that branch.
Reporting them here since they came out of reading it.

feat/vision-qwen3_5-full is now a08437f (was c08372d); a fetch of the same branch
picks both up.

/img in the terminal. The server takes images only as inline data: URLs, so until
now sending one meant writing a client or assembling the base64 by hand. ft shell now has
/img <path> [text] -- it reads the file, guesses the mime type, and puts the image ahead
of the text; repeat it to attach several. So a screenshot goes in directly:

> /img ~/shot.png what is the error on this screen?

FREETOKEN_LOAD_VISION=1 works again without --vision. All three processes that
build a model were pinning the gate to False on a bare ft serve, so the environment
variable could never be read. They now pin only when the flag is given, which means the
upstream env gate is enough on its own.

Both verified here on Ornith-1.5-35B-A3B-NVFP4 (RTX 4090, 24 GiB): a 448x448 PNG of three
shapes comes back named and coloured correctly, one image or several, with or without text
alongside it.

Assisted-by: Claude Opus 5